mm/swapops: rework swap entry manipulation code

Both migration and device private pages use special swap entries that are
manipluated by a range of inline functions.  The arguments to these are
somewhat inconsistent so rework them to remove flag type arguments and to
make the arguments similar for both read and write entry creation.

Link: https://lkml.kernel.org/r/20210616105937.23201-3-apopple@nvidia.comSigned-off-by: Alistair Popple <apopple@nvidia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Ralph Campbell <rcampbell@nvidia.com>
Cc: Ben Skeggs <bskeggs@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Peter Xu <peterx@redhat.com>
Cc: Shakeel Butt <shakeelb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

include/linux/swapops.h

@@ -107,35 +107,35 @@ static inline void *swp_to_radix_entry(swp_entry_t entry)
 }
 
 #if IS_ENABLED(CONFIG_DEVICE_PRIVATE)
-static inline swp_entry_t make_device_private_entry(struct page *page, bool write)
+static inline swp_entry_t make_readable_device_private_entry(pgoff_t offset)
 {
-	return swp_entry(write ? SWP_DEVICE_WRITE : SWP_DEVICE_READ,
-			 page_to_pfn(page));
+	return swp_entry(SWP_DEVICE_READ, offset);
 }
 
-static inline bool is_device_private_entry(swp_entry_t entry)
+static inline swp_entry_t make_writable_device_private_entry(pgoff_t offset)
 {
-	int type = swp_type(entry);
-	return type == SWP_DEVICE_READ || type == SWP_DEVICE_WRITE;
+	return swp_entry(SWP_DEVICE_WRITE, offset);
 }
 
-static inline void make_device_private_entry_read(swp_entry_t *entry)
+static inline bool is_device_private_entry(swp_entry_t entry)
 {
-	*entry = swp_entry(SWP_DEVICE_READ, swp_offset(*entry));
+	int type = swp_type(entry);
+	return type == SWP_DEVICE_READ || type == SWP_DEVICE_WRITE;
 }
 
-static inline bool is_write_device_private_entry(swp_entry_t entry)
+static inline bool is_writable_device_private_entry(swp_entry_t entry)
 {
 	return unlikely(swp_type(entry) == SWP_DEVICE_WRITE);
 }
 #else /* CONFIG_DEVICE_PRIVATE */
-static inline swp_entry_t make_device_private_entry(struct page *page, bool write)
+static inline swp_entry_t make_readable_device_private_entry(pgoff_t offset)
 {
 	return swp_entry(0, 0);
 }
 
-static inline void make_device_private_entry_read(swp_entry_t *entry)
+static inline swp_entry_t make_writable_device_private_entry(pgoff_t offset)
 {
+	return swp_entry(0, 0);
 }
 
 static inline bool is_device_private_entry(swp_entry_t entry)
@@ -143,35 +143,32 @@ static inline bool is_device_private_entry(swp_entry_t entry)
 	return false;
 }
 
-static inline bool is_write_device_private_entry(swp_entry_t entry)
+static inline bool is_writable_device_private_entry(swp_entry_t entry)
 {
 	return false;
 }
 #endif /* CONFIG_DEVICE_PRIVATE */
 
 #ifdef CONFIG_MIGRATION
-static inline swp_entry_t make_migration_entry(struct page *page, int write)
-{
-	BUG_ON(!PageLocked(compound_head(page)));
-
-	return swp_entry(write ? SWP_MIGRATION_WRITE : SWP_MIGRATION_READ,
-			page_to_pfn(page));
-}
-
 static inline int is_migration_entry(swp_entry_t entry)
 {
 	return unlikely(swp_type(entry) == SWP_MIGRATION_READ ||
 			swp_type(entry) == SWP_MIGRATION_WRITE);
 }
 
-static inline int is_write_migration_entry(swp_entry_t entry)
+static inline int is_writable_migration_entry(swp_entry_t entry)
 {
 	return unlikely(swp_type(entry) == SWP_MIGRATION_WRITE);
 }
 
-static inline void make_migration_entry_read(swp_entry_t *entry)
+static inline swp_entry_t make_readable_migration_entry(pgoff_t offset)
 {
-	*entry = swp_entry(SWP_MIGRATION_READ, swp_offset(*entry));
+	return swp_entry(SWP_MIGRATION_READ, offset);
+}
+
+static inline swp_entry_t make_writable_migration_entry(pgoff_t offset)
+{
+	return swp_entry(SWP_MIGRATION_WRITE, offset);
 }
 
 extern void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep,
@@ -181,21 +178,28 @@ extern void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
 extern void migration_entry_wait_huge(struct vm_area_struct *vma,
 		struct mm_struct *mm, pte_t *pte);
 #else
+static inline swp_entry_t make_readable_migration_entry(pgoff_t offset)
+{
+	return swp_entry(0, 0);
+}
+
+static inline swp_entry_t make_writable_migration_entry(pgoff_t offset)
+{
+	return swp_entry(0, 0);
+}
 
-#define make_migration_entry(page, write) swp_entry(0, 0)
 static inline int is_migration_entry(swp_entry_t swp)
 {
 	return 0;
 }
 
-static inline void make_migration_entry_read(swp_entry_t *entryp) { }
 static inline void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep,
 					spinlock_t *ptl) { }
 static inline void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
 					 unsigned long address) { }
 static inline void migration_entry_wait_huge(struct vm_area_struct *vma,
 		struct mm_struct *mm, pte_t *pte) { }
-static inline int is_write_migration_entry(swp_entry_t entry)
+static inline int is_writable_migration_entry(swp_entry_t entry)
 {
 	return 0;
 }

mm/debug_vm_pgtable.c

@@ -843,17 +843,17 @@ static void __init swap_migration_tests(void)
 	 * locked, otherwise it stumbles upon a BUG_ON().
 	 */
 	__SetPageLocked(page);
-	swp = make_migration_entry(page, 1);
+	swp = make_writable_migration_entry(page_to_pfn(page));
 	WARN_ON(!is_migration_entry(swp));
-	WARN_ON(!is_write_migration_entry(swp));
+	WARN_ON(!is_writable_migration_entry(swp));
 
-	make_migration_entry_read(&swp);
+	swp = make_readable_migration_entry(swp_offset(swp));
 	WARN_ON(!is_migration_entry(swp));
-	WARN_ON(is_write_migration_entry(swp));
+	WARN_ON(is_writable_migration_entry(swp));
 
-	swp = make_migration_entry(page, 0);
+	swp = make_readable_migration_entry(page_to_pfn(page));
 	WARN_ON(!is_migration_entry(swp));
-	WARN_ON(is_write_migration_entry(swp));
+	WARN_ON(is_writable_migration_entry(swp));
 	__ClearPageLocked(page);
 	__free_page(page);
 }

mm/hmm.c

@@ -255,7 +255,7 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
 		 */
 		if (hmm_is_device_private_entry(range, entry)) {
 			cpu_flags = HMM_PFN_VALID;
-			if (is_write_device_private_entry(entry))
+			if (is_writable_device_private_entry(entry))
 				cpu_flags |= HMM_PFN_WRITE;
 			*hmm_pfn = swp_offset(entry) | cpu_flags;
 			return 0;

mm/huge_memory.c

@@ -1054,8 +1054,9 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		swp_entry_t entry = pmd_to_swp_entry(pmd);
 
 		VM_BUG_ON(!is_pmd_migration_entry(pmd));
-		if (is_write_migration_entry(entry)) {
-			make_migration_entry_read(&entry);
+		if (is_writable_migration_entry(entry)) {
+			entry = make_readable_migration_entry(
+							swp_offset(entry));
 			pmd = swp_entry_to_pmd(entry);
 			if (pmd_swp_soft_dirty(*src_pmd))
 				pmd = pmd_swp_mksoft_dirty(pmd);
@@ -1772,13 +1773,14 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 		swp_entry_t entry = pmd_to_swp_entry(*pmd);
 
 		VM_BUG_ON(!is_pmd_migration_entry(*pmd));
-		if (is_write_migration_entry(entry)) {
+		if (is_writable_migration_entry(entry)) {
 			pmd_t newpmd;
 			/*
 			 * A protection check is difficult so
 			 * just be safe and disable write
 			 */
-			make_migration_entry_read(&entry);
+			entry = make_readable_migration_entry(
+							swp_offset(entry));
 			newpmd = swp_entry_to_pmd(entry);
 			if (pmd_swp_soft_dirty(*pmd))
 				newpmd = pmd_swp_mksoft_dirty(newpmd);
@@ -2067,7 +2069,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 
 		entry = pmd_to_swp_entry(old_pmd);
 		page = pfn_swap_entry_to_page(entry);
-		write = is_write_migration_entry(entry);
+		write = is_writable_migration_entry(entry);
 		young = false;
 		soft_dirty = pmd_swp_soft_dirty(old_pmd);
 		uffd_wp = pmd_swp_uffd_wp(old_pmd);
@@ -2099,7 +2101,12 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 		 */
 		if (freeze || pmd_migration) {
 			swp_entry_t swp_entry;
-			swp_entry = make_migration_entry(page + i, write);
+			if (write)
+				swp_entry = make_writable_migration_entry(
+							page_to_pfn(page + i));
+			else
+				swp_entry = make_readable_migration_entry(
+							page_to_pfn(page + i));
 			entry = swp_entry_to_pte(swp_entry);
 			if (soft_dirty)
 				entry = pte_swp_mksoft_dirty(entry);
@@ -3171,7 +3178,10 @@ void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
 	pmdval = pmdp_invalidate(vma, address, pvmw->pmd);
 	if (pmd_dirty(pmdval))
 		set_page_dirty(page);
-	entry = make_migration_entry(page, pmd_write(pmdval));
+	if (pmd_write(pmdval))
+		entry = make_writable_migration_entry(page_to_pfn(page));
+	else
+		entry = make_readable_migration_entry(page_to_pfn(page));
 	pmdswp = swp_entry_to_pmd(entry);
 	if (pmd_soft_dirty(pmdval))
 		pmdswp = pmd_swp_mksoft_dirty(pmdswp);
@@ -3197,7 +3207,7 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new)
 	pmde = pmd_mkold(mk_huge_pmd(new, vma->vm_page_prot));
 	if (pmd_swp_soft_dirty(*pvmw->pmd))
 		pmde = pmd_mksoft_dirty(pmde);
-	if (is_write_migration_entry(entry))
+	if (is_writable_migration_entry(entry))
 		pmde = maybe_pmd_mkwrite(pmde, vma);
 	if (pmd_swp_uffd_wp(*pvmw->pmd))
 		pmde = pmd_wrprotect(pmd_mkuffd_wp(pmde));

mm/hugetlb.c

@@ -4242,12 +4242,13 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 				    is_hugetlb_entry_hwpoisoned(entry))) {
 			swp_entry_t swp_entry = pte_to_swp_entry(entry);
 
-			if (is_write_migration_entry(swp_entry) && cow) {
+			if (is_writable_migration_entry(swp_entry) && cow) {
 				/*
 				 * COW mappings require pages in both
 				 * parent and child to be set to read.
 				 */
-				make_migration_entry_read(&swp_entry);
+				swp_entry = make_readable_migration_entry(
+							swp_offset(swp_entry));
 				entry = swp_entry_to_pte(swp_entry);
 				set_huge_swap_pte_at(src, addr, src_pte,
 						     entry, sz);
@@ -5532,10 +5533,11 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 		if (unlikely(is_hugetlb_entry_migration(pte))) {
 			swp_entry_t entry = pte_to_swp_entry(pte);
 
-			if (is_write_migration_entry(entry)) {
+			if (is_writable_migration_entry(entry)) {
 				pte_t newpte;
 
-				make_migration_entry_read(&entry);
+				entry = make_readable_migration_entry(
+							swp_offset(entry));
 				newpte = swp_entry_to_pte(entry);
 				set_huge_swap_pte_at(mm, address, ptep,
 						     newpte, huge_page_size(h));

mm/memory.c

@@ -733,13 +733,14 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 
 		rss[mm_counter(page)]++;
 
-		if (is_write_migration_entry(entry) &&
+		if (is_writable_migration_entry(entry) &&
 				is_cow_mapping(vm_flags)) {
 			/*
 			 * COW mappings require pages in both
 			 * parent and child to be set to read.
 			 */
-			make_migration_entry_read(&entry);
+			entry = make_readable_migration_entry(
+							swp_offset(entry));
 			pte = swp_entry_to_pte(entry);
 			if (pte_swp_soft_dirty(*src_pte))
 				pte = pte_swp_mksoft_dirty(pte);
@@ -770,9 +771,10 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		 * when a device driver is involved (you cannot easily
 		 * save and restore device driver state).
 		 */
-		if (is_write_device_private_entry(entry) &&
+		if (is_writable_device_private_entry(entry) &&
 		    is_cow_mapping(vm_flags)) {
-			make_device_private_entry_read(&entry);
+			entry = make_readable_device_private_entry(
+							swp_offset(entry));
 			pte = swp_entry_to_pte(entry);
 			if (pte_swp_uffd_wp(*src_pte))
 				pte = pte_swp_mkuffd_wp(pte);

mm/migrate.c

@@ -210,13 +210,18 @@ static bool remove_migration_pte(struct page *page, struct vm_area_struct *vma,
 		 * Recheck VMA as permissions can change since migration started
 		 */
 		entry = pte_to_swp_entry(*pvmw.pte);
-		if (is_write_migration_entry(entry))
+		if (is_writable_migration_entry(entry))
 			pte = maybe_mkwrite(pte, vma);
 		else if (pte_swp_uffd_wp(*pvmw.pte))
 			pte = pte_mkuffd_wp(pte);
 
 		if (unlikely(is_device_private_page(new))) {
-			entry = make_device_private_entry(new, pte_write(pte));
+			if (pte_write(pte))
+				entry = make_writable_device_private_entry(
+							page_to_pfn(new));
+			else
+				entry = make_readable_device_private_entry(
+							page_to_pfn(new));
 			pte = swp_entry_to_pte(entry);
 			if (pte_swp_soft_dirty(*pvmw.pte))
 				pte = pte_swp_mksoft_dirty(pte);
@@ -2297,7 +2302,7 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp,
 
 			mpfn = migrate_pfn(page_to_pfn(page)) |
 					MIGRATE_PFN_MIGRATE;
-			if (is_write_device_private_entry(entry))
+			if (is_writable_device_private_entry(entry))
 				mpfn |= MIGRATE_PFN_WRITE;
 		} else {
 			if (!(migrate->flags & MIGRATE_VMA_SELECT_SYSTEM))
@@ -2343,8 +2348,12 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp,
 			ptep_get_and_clear(mm, addr, ptep);
 
 			/* Setup special migration page table entry */
-			entry = make_migration_entry(page, mpfn &
-						     MIGRATE_PFN_WRITE);
+			if (mpfn & MIGRATE_PFN_WRITE)
+				entry = make_writable_migration_entry(
+							page_to_pfn(page));
+			else
+				entry = make_readable_migration_entry(
+							page_to_pfn(page));
 			swp_pte = swp_entry_to_pte(entry);
 			if (pte_present(pte)) {
 				if (pte_soft_dirty(pte))
@@ -2817,7 +2826,12 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate,
 		if (is_device_private_page(page)) {
 			swp_entry_t swp_entry;
 
-			swp_entry = make_device_private_entry(page, vma->vm_flags & VM_WRITE);
+			if (vma->vm_flags & VM_WRITE)
+				swp_entry = make_writable_device_private_entry(
+							page_to_pfn(page));
+			else
+				swp_entry = make_readable_device_private_entry(
+							page_to_pfn(page));
 			entry = swp_entry_to_pte(swp_entry);
 		} else {
 			/*

mm/mprotect.c

@@ -143,23 +143,25 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 			swp_entry_t entry = pte_to_swp_entry(oldpte);
 			pte_t newpte;
 
-			if (is_write_migration_entry(entry)) {
+			if (is_writable_migration_entry(entry)) {
 				/*
 				 * A protection check is difficult so
 				 * just be safe and disable write
 				 */
-				make_migration_entry_read(&entry);
+				entry = make_readable_migration_entry(
+							swp_offset(entry));
 				newpte = swp_entry_to_pte(entry);
 				if (pte_swp_soft_dirty(oldpte))
 					newpte = pte_swp_mksoft_dirty(newpte);
 				if (pte_swp_uffd_wp(oldpte))
 					newpte = pte_swp_mkuffd_wp(newpte);
-			} else if (is_write_device_private_entry(entry)) {
+			} else if (is_writable_device_private_entry(entry)) {
 				/*
 				 * We do not preserve soft-dirtiness. See
 				 * copy_one_pte() for explanation.
 				 */
-				make_device_private_entry_read(&entry);
+				entry = make_readable_device_private_entry(
+							swp_offset(entry));
 				newpte = swp_entry_to_pte(entry);
 				if (pte_swp_uffd_wp(oldpte))
 					newpte = pte_swp_mkuffd_wp(newpte);

mm/rmap.c

@@ -1533,7 +1533,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 			 * pte. do_swap_page() will wait until the migration
 			 * pte is removed and then restart fault handling.
 			 */
-			entry = make_migration_entry(page, 0);
+			entry = make_readable_migration_entry(page_to_pfn(page));
 			swp_pte = swp_entry_to_pte(entry);
 
 			/*
@@ -1629,8 +1629,12 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 			 * pte. do_swap_page() will wait until the migration
 			 * pte is removed and then restart fault handling.
 			 */
-			entry = make_migration_entry(subpage,
-					pte_write(pteval));
+			if (pte_write(pteval))
+				entry = make_writable_migration_entry(
+							page_to_pfn(subpage));
+			else
+				entry = make_readable_migration_entry(
+							page_to_pfn(subpage));
 			swp_pte = swp_entry_to_pte(entry);
 			if (pte_soft_dirty(pteval))
 				swp_pte = pte_swp_mksoft_dirty(swp_pte);